1,验证码识别接口代码
import json
import base64
import requests def shibie():
data = {}
path = "./img/"
file_name = "a.jpg"
with open(path + file_name, "rb") as f:
data0 = f.read()
data['image_base64'] = str(base64.b64encode(data0),'utf-8')
data['app_id'] = 'qq'
data['ocr_code'] = '0000'
headers={'Content-Type':'application/json'}
res = requests.post(url='https://nmd-ai.juxinli.com/ocr_captcha',headers=headers,data=json.dumps(data))
res = res.json()
return res['string']
2,验证码识别思路代码
import os
import pytesseract
from PIL import Image
from collections import defaultdict # tesseract.exe所在的文件路径
pytesseract.pytesseract.tesseract_cmd = 'D:/Tesseract-OCR/tesseract.exe' # 获取图片中像素点数量最多的像素
def get_threshold(image):
pixel_dict = defaultdict(int) # 像素及该像素出现次数的字典
rows, cols = image.size
for i in range(rows):
for j in range(cols):
pixel = image.getpixel((i, j))
pixel_dict[pixel] += 1 count_max = max(pixel_dict.values()) # 获取像素出现出多的次数
pixel_dict_reverse = {v: k for k, v in pixel_dict.items()}
threshold = pixel_dict_reverse[count_max] # 获取出现次数最多的像素点 return threshold # 按照阈值进行二值化处理
# threshold: 像素阈值
def get_bin_table(threshold):
# 获取灰度转二值的映射table
table = []
for i in range(256):
rate = 0.1 # 在threshold的适当范围内进行处理
if threshold * (1 - rate) <= i <= threshold * (1 + rate):
table.append(1)
else:
table.append(0)
return table # 去掉二值化处理后的图片中的噪声点
def cut_noise(image):
rows, cols = image.size # 图片的宽度和高度
change_pos = [] # 记录噪声点位置 # 遍历图片中的每个点,除掉边缘
for i in range(1, rows - 1):
for j in range(1, cols - 1):
# pixel_set用来记录该店附近的黑色像素的数量
pixel_set = []
# 取该点的邻域为以该点为中心的九宫格
for m in range(i - 1, i + 2):
for n in range(j - 1, j + 2):
if image.getpixel((m, n)) != 1: # 1为白色,0位黑色
pixel_set.append(image.getpixel((m, n))) # 如果该位置的九宫内的黑色数量小于等于4,则判断为噪声
if len(pixel_set) <= 4:
change_pos.append((i, j)) # 对相应位置进行像素修改,将噪声处的像素置为1(白色)
for pos in change_pos:
image.putpixel(pos, 1) return image # 返回修改后的图片 # 识别图片中的数字加字母
# 传入参数为图片路径,返回结果为:识别结果
def OCR_lmj(img_path):
image = Image.open(img_path) # 打开图片文件
imgry = image.convert('L') # 转化为灰度图 # 获取图片中的出现次数最多的像素,即为该图片的背景
max_pixel = get_threshold(imgry) # 将图片进行二值化处理
table = get_bin_table(threshold=max_pixel)
out = imgry.point(table, '1') # 去掉图片中的噪声(孤立点)
out = cut_noise(out) # 保存图片
# out.save('E://figures/img_gray.jpg') # 仅识别图片中的数字
# text = pytesseract.image_to_string(out, config='digits')
# 识别图片中的数字和字母
text = pytesseract.image_to_string(out) # 去掉识别结果中的特殊字符
exclude_char_list = ' .:\\|\'\"?![],()~@#$%^&*_+-={};<>/¥—'
text = ''.join([x for x in text if x not in exclude_char_list]) return text if __name__=='__main__':
a = OCR_lmj('D:\\jd\\img\\2.jpg')
print(a)